AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Invariant Models for Causal Transfer Learning

Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, Jonas Peters

JMLR 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 105 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use invariant-subset prediction instead of pooling the training tasksLinear regression with gene intervention data · Gene perturbation, non-causal problems (269 cases)test errorImproved
use invariant-subset prediction instead of pooling the training tasksLinear regression with gene intervention data · Gene perturbation, causal problems (39 cases)test errorNo clear effect
use invariant-subset prediction instead of pooling the training tasksLinear regression · School datasettest errorNo clear effect
set acceptance level delta to 0 so all subsets are accepted (ablation)Invariant subset search (DG) · Synthetic DG, 3 training taskstest squared errorHurt
use greedy search instead of full search with many predictorsInvariant subset search · Synthetic DG, p=30feasibility and runtime: 1.57 -> 0.0396 seconds at p=10Improved
increase the number of training tasks beyond fourInvariant subset search · Synthetic DGtest squared errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy